<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khanehzar-etal-2023-probing">
    <titleInfo>
        <title>Probing Power by Prompting: Harnessing Pre-trained Language Models for Power Connotation Framing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shima</namePart>
        <namePart type="family">Khanehzar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Trevor</namePart>
        <namePart type="family">Cohn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gosia</namePart>
        <namePart type="family">Mikolajczak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lea</namePart>
        <namePart type="family">Frermann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>When describing actions, subtle changes in word choice can evoke very different associations with the involved entities. For instance, a company ‘employing workers’ evokes a more positive connotation than the one ‘exploiting’ them. This concept is called connotation. This paper investigates whether pre-trained language models (PLMs) encode such subtle connotative information about power differentials between involved entities. We design a probing framework for power connotation, building on (CITATION)’s operationalization of connotation frames. We show that zero-shot prompting of PLMs leads to above chance prediction of power connotation, however fine-tuning PLMs using our framework drastically improves their accuracy. Using our fine-tuned models, we present a case study of power dynamics in US news reporting on immigration, showing the potential of our framework as a tool for understanding subtle bias in the media.</abstract>
    <identifier type="citekey">khanehzar-etal-2023-probing</identifier>
    <location>
        <url>https://aclanthology.org/2023.eacl-main.61</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>873</start>
            <end>885</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Probing Power by Prompting: Harnessing Pre-trained Language Models for Power Connotation Framing
%A Khanehzar, Shima
%A Cohn, Trevor
%A Mikolajczak, Gosia
%A Frermann, Lea
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F khanehzar-etal-2023-probing
%X When describing actions, subtle changes in word choice can evoke very different associations with the involved entities. For instance, a company ‘employing workers’ evokes a more positive connotation than the one ‘exploiting’ them. This concept is called connotation. This paper investigates whether pre-trained language models (PLMs) encode such subtle connotative information about power differentials between involved entities. We design a probing framework for power connotation, building on (CITATION)’s operationalization of connotation frames. We show that zero-shot prompting of PLMs leads to above chance prediction of power connotation, however fine-tuning PLMs using our framework drastically improves their accuracy. Using our fine-tuned models, we present a case study of power dynamics in US news reporting on immigration, showing the potential of our framework as a tool for understanding subtle bias in the media.
%U https://aclanthology.org/2023.eacl-main.61
%P 873-885

Markdown (Informal)

[Probing Power by Prompting: Harnessing Pre-trained Language Models for Power Connotation Framing](https://aclanthology.org/2023.eacl-main.61) (Khanehzar et al., EACL 2023)

• Probing Power by Prompting: Harnessing Pre-trained Language Models for Power Connotation Framing (Khanehzar et al., EACL 2023)

ACL

• Shima Khanehzar, Trevor Cohn, Gosia Mikolajczak, and Lea Frermann. 2023. Probing Power by Prompting: Harnessing Pre-trained Language Models for Power Connotation Framing. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 873–885, Dubrovnik, Croatia. Association for Computational Linguistics.